Search Results for author:
Found 69 papers, 37 papers with code
Learning Memory Augmented Cascading Network for Compressed Sensing of Images
The IDR module is designed to reconstruct the remaining details from the residual measurement vector, and MRU is employed to update the residual measurement vector and feed it into the next IDR module.
HybriMap: Hybrid Clues Utilization for Effective Vectorized HD Map Construction
Constructing vectorized high-definition maps from surround-view cameras has garnered significant attention in recent years.
Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Function
To address this RGB-TSDF distribution difference, we propose a two-stage network with a 3D RGB feature completion module that completes RGB features with meaningful values for occluded areas.
Negative-Binomial Randomized Gamma Markov Processes for Heterogeneous Overdispersed Count Time Series
Modeling count-valued time series has been receiving increasing attention since count time series naturally arise in physical and social domains.
A Saliency Enhanced Feature Fusion based multiscale RGB-D Salient Object Detection Network
SEFF utilizes saliency maps of the neighboring scales to enhance the necessary features for fusing, resulting in more representative fused features.
Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data.
Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
Therefore, we explore the use of image segmentation foundation models to automatically generate training labels for 3D segmentation.
SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
Both quantitative and qualitative results on this evaluation dataset indicate that our SmartEdit surpasses previous methods, paving the way for the practical application of complex instruction-based image editing.
C-NERF: Representing Scene Changes as Directional Consistency Difference-based NeRF
Our approach surpasses state-of-the-art 2D change detection and NeRF-based methods by a significant margin.
Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields.
Catalytic activity prediction
Chemical-Disease Interaction Extraction
+14
Producing Usable Taxonomies Cheaply and Rapidly at Pinterest Using Discovered Dynamic $μ$-Topics
Creating a taxonomy of interests is expensive and human-effort intensive: not only do we need to identify nodes and interconnect them, in order to use the taxonomy, we must also connect the nodes to relevant entities such as users, pins, and queries.
Joint Representation Learning for Text and 3D Point Cloud
During the pre-training stage, we establish the correspondence of images and point clouds based on the readily available RGB-D data and use contrastive learning to align the image and point cloud representations.
Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space
Specifically, cheap scene graph supervision data can be easily obtained by parsing image language descriptions into semantic graphs.
A Faster, Lighter and Stronger Deep Learning-Based Approach for Place Recognition
We designed RepVGG-lite as the backbone network in our architecture, it is more discriminative than other general networks in the Place Recognition task.
Background-Mixed Augmentation for Weakly Supervised Change Detection
Change detection (CD) is to decouple object changes (i. e., object missing or appearing) from background changes (i. e., environment variations) like light and season variations in two images captured in the same scene over a long time span, presenting critical applications in disaster management, urban development, etc.
Cross-Modal Adapter for Text-Video Retrieval
However, as pre-trained models are scaling up, fully fine-tuning them on text-video retrieval datasets has a high risk of overfitting.
Rate-Splitting for Intelligent Reflecting Surface-Aided Multiuser VR Streaming
In the proposed system, RS facilitates the exploitation of the shared interests of the users in VR streaming, and IRS creates additional propagation channels to support the transmission of high-resolution 360-degree videos.
Efficient Knowledge Distillation from Model Checkpoints
Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers).
RenderNet: Visual Relocalization Using Virtual Viewpoints in Large-Scale Indoor Environments
Visual relocalization has been a widely discussed problem in 3D vision: given a pre-constructed 3D visual map, the 6 DoF (Degrees-of-Freedom) pose of a query image is estimated.
Deep Semantic Statistics Matching (D2SM) Denoising Network
The ultimate aim of image restoration like denoising is to find an exact correlation between the noisy and clear image domains.
IDET: Iterative Difference-Enhanced Transformers for High-Quality Change Detection
Change detection (CD) aims to detect change regions within an image pair captured at different times, playing a significant role in diverse real-world applications.
Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection
Such design decomposes the process of HOI set prediction into two subsequent phases, i. e., an interaction proposal generation is first performed, and then followed by transforming the non-parametric interaction proposals into HOI predictions via a structure-aware Transformer.
Ranked #3 on
Human-Object Interaction Detection
on V-COCO
Revisiting the role of heterophily in graph representation learning: An edge classification perspective
Alternatively, it is possible to exploit the information about the presence of heterophilous neighbors for feature learning, so a hybrid message passing approach is devised to aggregate homophilious neighbors and diversify heterophilous neighbors based on edge classification.
Co-visual pattern augmented generative transformer learning for automobile geo-localization
Geolocation is a fundamental component of route planning and navigation for unmanned vehicles, but GNSS-based geolocation fails under denial-of-service conditions.
Domain Adaptation via Prompt Learning
Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given.
Salient-to-Broad Transition for Video Person Re-Identification
To further improve SBM, an Integration-and-Distribution Module (IDM) is introduced to enhance frame-level representations.
Fully Attentional Network for Semantic Segmentation
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation.
Coupled Segmentation and Edge Learning via Dynamic Graph Propagation
It is therefore interesting to study how these two tasks can be coupled to benefit each other.
Denoised Non-Local Neural Network for Semantic Segmentation
Without any external training data, our proposed Denoised NL can achieve the state-of-the-art performance of 83. 5\% and 46. 69\% mIoU on Cityscapes and ADE20K, respectively.
PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation
Unsupervised learning of depth from indoor monocular videos is challenging as the artificial environment contains many textureless regions.
On the Importance of Gradients for Detecting Distributional Shifts in the Wild
Detecting out-of-distribution (OOD) data has become a critical component in ensuring the safe deployment of machine learning models in the real world.
Ranked #12 on
Out-of-Distribution Detection
on ImageNet-1k vs SUN
Domain Composition and Attention for Unseen-Domain Generalizable Medical Image Segmentation
First, we present a domain composition method that represents one certain domain by a linear combination of a set of basis representations (i. e., a representation bank).
Unsupervised Monocular Depth Perception: Focusing on Moving Objects
We first propose an outlier masking technique that considers the occluded or dynamic pixels as statistical outliers in the photometric error map.
IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement
3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level features.
Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models
We integrate this ranking scheme with two frequency models and a GPT-2 styled language model, along with the acceptance model to yield 27. 80% and 37. 64% increase in TOP1 and TOP5 accuracy, respectively.
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
Inspired by this phenomenon, we propose a Dynamic Transformer to automatically configure a proper number of tokens for each input image.
Ranked #29 on
Image Classification
on CIFAR-100
(using extra training data)
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world.
Ranked #3 on
Out-of-Distribution Detection
on ImageNet-1k vs iNaturalist
(using extra training data)
BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification
Detail Branch processes frames at original resolution to preserve the detailed visual clues, and Context Branch with a down-sampling strategy is employed to capture long-range contexts.
FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
Radiotherapy is a treatment where radiation is used to eliminate cancer cells.
SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom
Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images.
Learning Camera Localization via Dense Scene Matching
We present a new method for scene agnostic camera localization using dense scene matching (DSM), where a cost volume is constructed between a query image and a scene.
AR Mapping: Accurate and Efficient Mapping for Augmented Reality
Secondly, we propose an AR mapping pipeline which takes the input from the scanning device and produces accurate AR Maps.
AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing
In this paper, we propose a new model, called Attention-Augmented Network (AttaNet), to capture both global context and multilevel semantics while keeping the efficiency high.
UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation
Besides, we also designed a more effective fusion module for our fusion scheme.
Ranked #1 on
Depth Estimation
on Matterport3D
Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
Despite the stateof-the-art performance achieved by Convolutional Neural Networks (CNNs) for automatic segmentation of OARs, existing methods do not provide uncertainty estimation of the segmentation results for treatment planning, and their accuracy is still limited by several factors, including the low contrast of soft tissues in CT, highly imbalanced sizes of OARs and large inter-slice spacing.
Throughput Optimization for Grant-Free Multiple Access With Multiagent Deep Reinforcement Learning
Grant-free multiple access (GFMA) is a promising paradigm to efficiently support uplink access of Internet of Things (IoT) devices.
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection
Spotting objects that are visually adapted to their surroundings is challenging for both humans and AI.
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.
Ranked #3 on
3D Semantic Scene Completion
on SemanticKITTI
3D Semantic Scene Completion from a single RGB image
3D Semantic Segmentation
+3
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images.
Concentrated Multi-Grained Multi-Attention Network for Video Based Person Re-Identification
The attention mechanism has been proved to be helpful in solving the occlusion problem by a large number of existing methods.
CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation
Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object.
Multi-organ Segmentation via Co-training Weight-averaged Models from Few-organ Datasets
In most scenarios, one might obtain annotations of a single or a few organs from one training set, and obtain annotations of the the other organs from another set of training images.
Global Optimum Search in Quantum Deep Learning
This paper aims to solve machine learning optimization problem by using quantum circuit.
An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds
We use a U-Net style 3D sparse convolution network to extract features for each frame's LiDAR point-cloud.
Disentangle Perceptual Learning through Online Contrastive Learning
Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on the pre-trained classification network to provide features, which are not necessarily optimal in terms of visual perception of image transformation.
DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos
Unsupervised learning of depth and ego-motion from unlabelled monocular videos has recently drawn great attention, which avoids the use of expensive ground truth in the supervised one.
Ranked #52 on
Monocular Depth Estimation
on KITTI Eigen split
HighEr-Resolution Network for Image Demosaicing and Enhancing
However, plenty of studies have shown that global information is crucial for image restoration tasks like image demosaicing and enhancing.
Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching.
FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images
In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images.
How Effectively Can Indoor Wireless Positioning Relieve Visual Tracking Pains: A Camera-Rao Bound Viewpoint
Visual tracking is fragile in some difficult scenarios, for instance, appearance ambiguity and variation, occlusion can easily degrade most of visual trackers to some extent.
ClickBAIT-v2: Training an Object Detector in Real-Time
Modern deep convolutional neural networks (CNNs) for image classification and object detection are often trained offline on large static datasets.
Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly
Designing a robust affinity model is the key issue in multiple target tracking (MTT).
Learning Dynamic Siamese Network for Visual Object Tracking
How to effectively learn temporal variation of target appearance, to exclude the interference of cluttered background, while maintaining real-time response, is an essential problem of visual object tracking.
Ranked #5 on
Visual Object Tracking
on OTB-2013
Active Image-based Modeling with a Toy Drone
Image-based modeling techniques can now generate photo-realistic 3D models from images.
Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
A Spatio-Temporal Appearance Representation for Viceo-Based Pedestrian Re-Identification
Pedestrian re-identification is a difficult problem due to the large variations in a person's appearance caused by different poses and viewpoints, illumination changes, and occlusions.
Recognizing Focal Liver Lesions in Contrast-Enhanced Ultrasound with Discriminatively Trained Spatio-Temporal Model
The aim of this study is to provide an automatic computational framework to assist clinicians in diagnosing Focal Liver Lesions (FLLs) in Contrast-Enhancement Ultrasound (CEUS).
An Expressive Deep Model for Human Action Parsing from A Single Image
This paper aims at one newly raising task in vision and multimedia research: recognizing human actions from still images.
Exemplar-based Linear Discriminant Analysis for Robust Object Tracking
However, the task in tracking is to search for a specific object, rather than an object category as in detection.
